Negociación algorítmica de acciones por medio de aprendizaje por refuerzo profundo

dc.contributor.advisorVilla Garzón, Fernán Alonso
dc.contributor.advisorCortés Durán, Lina Marcela
dc.contributor.authorGiraldo Escobar, Santiago Alberto
dc.date.accessioned2021-12-06T18:15:53Z
dc.date.available2021-12-06T18:15:53Z
dc.date.issued2021-12-02
dc.descriptionilustraciones, gráficos, tablasspa
dc.description.abstractEste trabajo de grado tiene como finalidad explorar la utilización de series de tiempo financieras sintéticas generadas por un modelo de Redes Neuronales Generativas Adversarias (GAN por sus siglas en inglés) para entrenar un algoritmo de Aprendizaje Profundo Q Por Refuerzo que ejecute acciones de compra y venta para un título del mercado de valores del índice de Standard & Poor’s 500. Para el desarrollo del trabajo se empleó la metodología CRISP DM propuesta por IBM, entendiendo primero el negocio y la teoría necesaria para desarrollar los modelos, para continuar con la exploración y conocimiento de los datos disponibles que concordaran con los objetivos del estudio. En este se desarrolla un procedimiento para la selección de series ficticias y para el entrenamiento de un algoritmo por refuerzo con estos datos. Se utiliza la métrica de Kolmogorov - Smirnov como componente esencial para entrenar las redes GAN. Se explican los resultados de los experimentos, y se evidencia la dificultad para calibrar modelos generativos adversarios y de agentes entrenados por refuerzo. Por último, se presentan las conclusiones derivadas del trabajo y posibles investigaciones futuras. (Texto tomado de la fuente)spa
dc.description.abstractThis degree work aims to explore the use of synthetic financial time series generated by a Generative Adversarial Neural Networks (GAN) model to train a Deep Reinforcement Learning algorithm that executes buy and sell actions for a stock in the Standard & Poor's 500 index. For the implementation of the study, we used the CRISP methodology proposed by IBM, understanding first the business and the theory necessary to develop the models, to continue with the exploration and knowledge of the available data that matched the objectives of the project. In this paper, a procedure for selecting synthetic series and training a reinforcement algorithm with these data is developed. The Kolmogorov-Smirnov metric is used as an essential component to train GANs. The results of the experiments are explained, and the difficulty in calibrating generative adversarial and reinforcement network models is shown. Finally, conclusions derived from the project and possible future research are presented.eng
dc.description.curricularareaÁrea Curricular de Ingeniería de Sistemas e Informáticaspa
dc.description.degreelevelMaestríaspa
dc.description.degreenameMagíster en Ingeniería – Ingeniería de Sistemasspa
dc.format.extent72 páginasspa
dc.format.mimetypeapplication/pdfspa
dc.identifier.instnameUniversidad Nacional de Colombiaspa
dc.identifier.reponameRepositorio Institucional Universidad Nacional de Colombiaspa
dc.identifier.repourlhttps://repositorio.unal.edu.co/spa
dc.identifier.urihttps://repositorio.unal.edu.co/handle/unal/80758
dc.language.isospaspa
dc.publisherUniversidad Nacional de Colombiaspa
dc.publisher.branchUniversidad Nacional de Colombia - Sede Medellínspa
dc.publisher.departmentDepartamento de la Computación y la Decisiónspa
dc.publisher.facultyFacultad de Minasspa
dc.publisher.placeMedellín, Colombiaspa
dc.publisher.programMedellín - Minas - Maestría en Ingeniería - Ingeniería de Sistemasspa
dc.relation.referencesA. Charpentier, R. Elie and C. Remlinger. "Reinforcement Learning in Economics and Finance". 2020. arXiv:2003.10014v1.spa
dc.relation.referencesA. Mosavi, Y. Faghan, P. Ghamisi, P. Duan, S. F. Ardabili, E. Salwana and S. S. Band. "Comprehensive Review of Deep Reinforcement Learning Methods and Applications in Economics". Mathematics 2020, 8, 1640. DOI: 10.3390/math8101640.spa
dc.relation.referencesA. Ozbayoglu, M. Gudelek, and O. Sezer. "Deep learning for financial applications: A survey". Applied Soft Computing Journal 93 (2020) 106384. Doi: 10.1016/j.asoc.2020.106384.spa
dc.relation.referencesB.M. Henrique, V.A. Sobreiro and H. Kimura. "Literature review: Machine learning techniques applied to financial market prediction". Expert Systems With Applications 124 (2019) 226–251. Doi: 10.1016/j.eswa.2019.01.012.spa
dc.relation.referencesC. Lattemann, P. Loos, j. Gomolka, H.P. Burghof, A. Breuer A, Gomber P, M. Krogmann, J. Nagel, R. Riess, R. Riordan, R.Zajonz (2012) High Frequency Trading. Kosten und Nutzen im Wertpapierhandel und Notwendigkeit der Marktregulierung. WIRTSCHAFTSINFORMATIK. Gabler Verlag. Doi: 10.1007/s11576-012-0311-9.spa
dc.relation.referencesD. Lv, S. Yuan, M. Li and Y. Xiang. “An Empirical Study of Machine Learning Algorithms for Stock Daily Trading Strategy”. Mathematical Problems in Engineering. Volume 2019, Article ID 7816154, 30 pages. Doi: 10.1155/2019/7816154.spa
dc.relation.referencesE. Benhamou, D. Saltiel, S. Ungari, A. Mukhopadhyay and J. Atif. "AAMDRL: Augmented Asset Management with Deep Reinforcement Learning". 2020. arXiv:2010.08497v1.spa
dc.relation.referencesE. Villarraga. “Generación de series de tiempo financieras sintéticas para “data augmentation” usando Redes Neuronales Generativas Adversarias (GAN)”. Trabajo Final. Universidad Nacional de Colombia. 2021.spa
dc.relation.referencesF. Rundo, F. Trenta, A. Luigi di Stallo and S. Battiato. "Machine Learning for Quantitative Finance Applications: A Survey". Applied Sciences. 2019, 9, 5574. Doi: 10.3390/app9245574.spa
dc.relation.referencesG. W. Corder and D. I. Foreman. "Nonparametric statistics: a step-by-step approach". 2nd ed. Wiley. 2014.spa
dc.relation.referencesG.N. Gregoriou. "The Handbook of HIGH FREQUENCY TRADING". Elsevier Inc. 2015.spa
dc.relation.referencesH. Dong, Z. Ding and S. Zhang. "Deep Reinforcement Learning, An introduction". Springer Nature Singapore Pte Ltd. 2020. doi:10.1007/978-981-15-4095-0.spa
dc.relation.referencesH. Tatsat, S. Puri, and B. Lookabaugh. "Machine Learning and Data Science Blueprints for Finance - From Building Trading Strategies to Robo-Advisors Using Python". O’Reilly. 2021.spa
dc.relation.referencesI. Goodfellow, Y. Bengio, and A. Courville. “Deep Learning”. The MIT Press. 2016.spa
dc.relation.referencesJ. Brownlee. “Generative Adversarial Networks with Python”. Jason Brownlee. 2019.spa
dc.relation.referencesJ. Langr and V. Bok. “GANs in Action”. Manning. 2019.spa
dc.relation.referencesJ. Schmidhuber. “Generative Adversarial Networks are Special Cases of Artificial Curiosity (1990) and also Closely Related to Predictability Minimization (1991)”. 2020. ArXiv:1906.04493v3.spa
dc.relation.referencesK. Arulkumaran, M. P. Deisenroth, M. Brundage, and A. A. Bharath. "Deep Reinforcement Learning - A brief survey". IEEE Signal Processing Magazine. November 2017. DOI: 10.1109/MSP.2017.2743240.spa
dc.relation.referencesK. B. Hansen. “The virtue of simplicity: On machine learning models in algorithmic trading”. Big Data & Society. 2020. Doi: 10.1177/2053951720926558.spa
dc.relation.referencesK. Lei, B. Zhang, Y. Li, M. Yang, and Y. Shen. "Time-driven feature-aware jointly deep reinforcement learning for financial signal representation and algorithmic trading". Expert Systems With Applications 140 (2020) 112872. DOI: 10.1016/j.eswa.2019.112872.spa
dc.relation.referencesL. Ryll and S. Seidens. "Evaluating the Performance of Machine Learning Algorithms in Financial Market Forecasting: A Comprehensive Survey". 2019. arXiv:1906.07786v2.spa
dc.relation.referencesM. Karpe. "An overall view of key problems in algorithmic trading and recent progress". 2020. arXiv:2006.05515v1.spa
dc.relation.referencesM. López de Prado, Marcos. "The Future of Empirical Finance". Journal of Portfolio Management, 41(4), 2015. Doi: 10.2139/ssrn.2609734.spa
dc.relation.referencesM. López de Prado. "The 10 Reasons Most Machine Learning Funds Fail". JPM 2018, 44 (6) 120-133 doi: 10.3905/jpm.2018.44.6.120.spa
dc.relation.referencesM. López de Prado. “Advances in Financial Machine Learning”. Wiley. 2018.spa
dc.relation.referencesM. López de Prado. “Tactical Investment Algorithms”. 2019. Available at SSRN: https://ssrn.com/abstract=3459866 or http://dx.doi.org/10.2139/ssrn.3459866.spa
dc.relation.referencesM. Wiese, R. Knobloch, R. Korn, and P. Kretschmer. "Quant GANs: Deep Generation of Financial Time Series". 2019. arXiv:1907.06673v2.spa
dc.relation.referencesP. Brandimarte. "Handbook in Monte Carlo simulation: applications in financial engineering, risk management, and economics". Wiley. 2014.spa
dc.relation.referencesP. Kolm and G. Ritter, “Modern Perspectives on Reinforcement Learning in Finance”. The Journal of Machine Learning in Finance, Vol. 1, No. 1, 2020. Doi:10.2139/ssrn.3449401.spa
dc.relation.referencesP. Treleaven, M. Galas, and V. Lalchand. "Algorithmic Trading Review". Communications of the ACM. november 2013. Vol. 56, no. 11. Doi: 10.1145/2500117.spa
dc.relation.referencesR. A. Brealey, S. C. Myers, and R. C. Merton. "Principles of Corporate Finance". 12 Edition. McGraw-Hill. 2017.spa
dc.relation.referencesR. Fu, J. Chen, S. Zeng, Y. Zhuang and A. Sudjianto. “Time Series Simulation by Conditional Generative Adversarial Net”. 2019. arXiv:1904.11419.spa
dc.relation.referencesR. S. Sutton and A. G. Barto. "Reinforcement Learning: An Introduction" second edition The MIT Press. 2018.spa
dc.relation.referencesR. Tsay. "Analysis of financial time series". 3rd ed. Wiley. 2010.spa
dc.relation.referencesS. Assefa, D. Dervovic, M. Mahfouz, T. Balch, P. Reddy, and M. Veloso. "Generating Synthetic Data in Finance: Opportunities, Challenges and Pitfalls". In NeurIPS'19 Workshop on Robust AI in Financial Services, Vancouver, Canada, December 2019.spa
dc.relation.referencesS. Nosratabadi, A. Mosavi, P. Duan, P. Ghamisi, F. Filip, S. S. Band, U. Reuter, J. Gama and A. H. Gandomi. "Data Science in Economics: Comprehensive Review of Advanced Machine Learning and Deep Learning Methods". Mathematics 2020, 8, 1799; Doi: 10.3390/math8101799.spa
dc.relation.referencesS. Takahashi, Y. Chen and K. Tanaka-Ishii. "Modeling financial time-series with generative adversarial networks". Physica A 527 (2019) 121261. DOI: 10.1016/j.physa.2019.121261.spa
dc.relation.referencesT. G. Fischer, “Reinforcement learning in financial markets - a survey”. FAU Discussion Papers in Economics, No. 12/2018, Friedrich-Alexander-Universität Erlangen-Nürnberg, Institute for Economics, Nürnberg. 2018.spa
dc.relation.referencesV. Bacoyannis, V. Glukhov, T. Jin, J. Kochems, and D. R. Song. “Idiosyncrasies and challenges of data driven learning in electronic trading”. 2018. arXiv:1811.09549v2.spa
dc.relation.referencesV. François-Lavet, P. Henderson, R. Islam, M. G. Bellemare and J. Pineau, “An Introduction to Deep Reinforcement Learning”, Foundations and Trends in Machine Learning: Vol. 11, No. 3-4. Doi: 10.1561/2200000071.spa
dc.relation.referencesY. Hilpisch. “Python for Algorithmic Trading - From Idea to Cloud Deployment”. O’Reilly Media, Inc. 2020.spa
dc.relation.referencesY. Hilpisch. “Artificial Intelligence in Finance - A Python-Based Guide”. O’Reilly Media, Inc. 2021.spa
dc.relation.referencesY. Sato. "Model-Free Reinforcement Learning for Financial Portfolios: A Brief Survey". 2019. arXiv:1904.04973v2.spa
dc.relation.referencesZ. Kakushadze and J. Serur. “151 Trading Strategies”. Palgrave Macmillan. 2018.spa
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.rights.licenseAtribución-CompartirIgual 4.0 Internacionalspa
dc.rights.urihttp://creativecommons.org/licenses/by-sa/4.0/spa
dc.subject.ddc000 - Ciencias de la computación, información y obras generales::003 - Sistemasspa
dc.subject.ddc620 - Ingeniería y operaciones afines::629 - Otras ramas de la ingenieríaspa
dc.subject.otherRedes Neuronales Generativas Adversariasspa
dc.subject.proposalAprendizaje profundospa
dc.subject.proposalAprendizaje por refuerzo profundospa
dc.subject.proposalRedes neuronales generativas adversariasspa
dc.subject.proposalNegociación algorítmicaspa
dc.subject.proposalAprendizaje de máquinaspa
dc.subject.proposalNegociación de accionesspa
dc.subject.proposalDeep learningeng
dc.subject.proposalDeep reinforcement learningeng
dc.subject.proposalGenerative Adversarial Networkseng
dc.subject.proposalAlgorithmic tradingeng
dc.subject.proposalMachine learningeng
dc.subject.proposalStock tradingeng
dc.titleNegociación algorítmica de acciones por medio de aprendizaje por refuerzo profundospa
dc.title.translatedAlgorithmic stock trading through deep reinforcement learningeng
dc.typeTrabajo de grado - Maestríaspa
dc.type.coarhttp://purl.org/coar/resource_type/c_bdccspa
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aaspa
dc.type.contentTextspa
dc.type.driverinfo:eu-repo/semantics/masterThesisspa
dc.type.redcolhttp://purl.org/redcol/resource_type/TMspa
dc.type.versioninfo:eu-repo/semantics/acceptedVersionspa
dcterms.audience.professionaldevelopmentEstudiantesspa
dcterms.audience.professionaldevelopmentInvestigadoresspa
dcterms.audience.professionaldevelopmentMaestrosspa
oaire.accessrightshttp://purl.org/coar/access_right/c_abf2spa

Archivos

Bloque original

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
98554412.2021.pdf
Tamaño:
2.71 MB
Formato:
Adobe Portable Document Format
Descripción:
Tesis de Maestría en Ingeniería - Ingeniería de Sistemas

Bloque de licencias

Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
3.98 KB
Formato:
Item-specific license agreed upon to submission
Descripción: